What is neuron-framework-autoport?

A workflow for adapting a Hugging Face model from PyTorch on NVIDIA GPUs to PyTorch with Neuron support on AWS Trainium or Inferentia chips. It covers dependency setup, architecture review, implementation, and compilation steps.

Use it when porting, auto-porting, or compiling a Hugging Face model for Trainium or Inferentia, including dry-run preparation.

It provides a defined process for moving a model to AWS hardware with the required Neuron libraries and checks. A dry run can inspect the setup without compiling or running inference.

neuron-framework-autoport — Skill for Claude Code by aws-neuron

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add aws-neuron/neuron-agentic-development --skill neuron-framework-autoport

Clone the repo

git clone --depth 1 https://github.com/aws-neuron/neuron-agentic-development

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/aws-neuron/neuron-agentic-development/neuron-framework-autoport/github.svg)](https://agentmods.dev/skills/aws-neuron/neuron-agentic-development/neuron-framework-autoport)

Your own site

<a href="https://agentmods.dev/skills/aws-neuron/neuron-agentic-development/neuron-framework-autoport"><img src="https://agentmods.dev/badge/skills/aws-neuron/neuron-agentic-development/neuron-framework-autoport/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/aws-neuron/neuron-agentic-development/neuron-framework-autoport"><img src="https://agentmods.dev/badge/skills/aws-neuron/neuron-agentic-development/neuron-framework-autoport.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,196 The whole file, excluding the scripts and references it only reads on demand.

Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00094	$0.02196
Opus 5.5	$0.00038	$0.00878
Sonnet 5.5	$0.00019	$0.00439
Haiku 4.5	$0.00009	$0.00220

Measured 1mo ago against content hash 34bb0f548ce5, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade D, and why

neuron-framework-autoport scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 14 executable files (assets/example_gptoss_usage.py, assets/example_phi3_usage.py, assets/example_phimoe_usage.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- **Do not run any code** — no compilation, inference, or validation (no Trainium hardware available)

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

2. Delete compiled model: `rm -rf agent_artifacts/data/compiled_model && rm -rf /var/tmp/neuron-compile-cache`

skills/neuron-framework-autoport/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Model Porting

Overview

This document provides the agent direct instructions on how to port a model from pytorch and running on NVIDIA GPU to pytorch/Neuron running on Trainium. The agent will be expected to follow these steps below.

Pay attention to the success criteria, do not stop, or declare that you are done until you meet the complete success criteria

Dry-run

When the user specifies dry-run:

Skip the "Resolve Dependencies" step

Run these commands to activate the venv and resolve source paths:

export PATH=<pathToVenv>/bin:$PATH
NXDI_SRC=$(python3 -c "import neuronx_distributed_inference; print(neuronx_distributed_inference.__path__[0])")
NXD_SRC=$(python3 -c "import neuronx_distributed; print(neuronx_distributed.__path__[0])")
TRANSFORMERS_SRC=$(python3 -c "import transformers; print(transformers.__path__[0])")

Do not run any code — no compilation, inference, or validation (no Trainium hardware available)

Before You Start

Set User Invocation Directory

USER_INVOCATION_DIR="$(pwd)"

Resolve Dependencies

Follow references/setup_flow.md. It handles venv validation, install consent, and exit code recovery. Do not proceed until it completes successfully.

After success, retain the 3 resolved paths from the script output for use throughout the workflow:

Variable	Description
`${NXDI_SRC}`	Path to NeuronX Distributed Inference source
`${NXD_SRC}`	Path to NeuronX Distributed source
`${TRANSFORMERS_SRC}`	Path to HuggingFace Transformers source

Read Project Guidelines

READ references/systemPrompts/systemPrompt.md in this skill directory. It contains prerequisites (including version checks), project guidelines, tool documentation, debugging support, codebase navigation, and hardware context. Run all prerequisite checks and follow all guidelines throughout the workflow.

Porting Parameters

Extract these six required parameters from the user's request before starting:

Read the full file on GitHub · 130 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 130 lines · 94 tokens per session scan D 34bb0f548ce5

Subscribe to this mod's changes

neuron-framework-autoport is a skill published in the GitHub repository aws-neuron/neuron-agentic-development (63 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 94 tokens to every session and 2,196 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it D with 2 findings (unrestricted tool access, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI Hardware and IoT

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-memory-thermal-ops

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

wshobson/agents · 59 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

amc-run-rtsp-calibration

Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.

NVIDIA/skills · 59 tokens

deepstream-generate-pipeline

Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming — including natural phrases like 'pipeline to infer on image', 'run inference on video', 'detect objects in stream', 'save inference output', 'deepstream pipeline'…

NVIDIA/skills · 108 tokens

neuron-framework-autoport